Gemini 2.5 Flash vs GPT-4o mini
GPT-4o mini is the cheaper of the 2: for the same tokens, 3 read for each 1 written, Gemini 2.5 Flash costs 3.2 times as much. Below are both price lists, what 8 everyday jobs cost a month on each, and how many tokens the same text takes on each, which can change the answer.
- For the same tokens
- GPT-4o mini is cheaper; Gemini 2.5 Flash costs 3.2 times as much
- Cheaper to read
- GPT-4o mini, $0.15 against $0.30
- Cheaper to write
- GPT-4o mini, $0.60 against $2.50
- Scores higher
- Not known, Gemini 2.5 Flash has no independent score yet
- Larger window
- Gemini 2.5 Flash, 1.05M against 128K tokens
Price per million tokens, side by side
In US dollars, as each maker prints them. The better figure in each row is green.
| Gemini 2.5 FlashGoogle · earlier model | GPT-4o miniOpenAI · earlier model | |
|---|---|---|
| InputTokens the model reads | $0.30 | $0.15 |
| Cached inputRead again from the cache | $0.03 | $0.075 |
| Cache writePutting text in the cache | Not listed | Not listed |
| OutputTokens it writes, thinking included | $2.50 | $0.60 |
| Blend 3:13 tokens read for each 1 written | $0.85 | $0.2625 |
| Batch inputAnswers collected later | Not listed | $0.075 |
| Batch output | Not listed | $0.30 |
| Context windowTokens it holds at once | 1.05M | 128K |
| Capability scoreEpoch Capabilities Index; GPT-5 is 150 | Not listed | 127 |
| Longest answerTokens it writes in 1 reply | 66K | 16K |
Read before you choose
- Gemini 2.5 Flash: Audio input is $1.
The same text, counted by each maker
A price per token means little until you know how many tokens your text is. Here is our lesson How AI writes, about 1,700 words of English, counted the way each maker counts it, and what it costs to send it once.
Gemini 2.5 Flash
about 2,200 tokens
Sent once: 0.066 cents at $0.30 per million
Google does not publish the Gemini tokenizer. Its rule is that a token is about 4 characters, so the count is the characters divided by 4.
GPT-4o mini
about 2,100 tokens
Sent once: 0.031 cents at $0.15 per million
GPT-5.6 is counted with o200k_base, the tokenizer OpenAI publishes for it, so its count is exact. OpenAI has not published the tokenizer of GPT-6, so its count is the same o200k_base figure, marked as about.
What 8 everyday jobs cost a month on each
Each job at its usual number of runs a day, for 30 days, at the standard price. The cheaper of the 2 is green; open any job in the calculator to change it. Sizes are in tokens, and Gemini 2.5 Flash can need up to 1.1 times as many as GPT-4o mini for the same words, so its bill for the same work can be up to that much higher.
| Job | Gemini 2.5 Flash | GPT-4o mini | Difference |
|---|---|---|---|
| A chat question300 in, 500 out, 100 a day | $4.020.13 cents a run | $1.040.034 cents a run | 3.9 times |
| A hard question, with thinking300 in, 1,400 out, 100 a day | $10.770.36 cents a run | $2.660.088 cents a run | 4.1 times |
| A long report, summarised60,000 in, 2,000 out, 20 a day | $13.802.3 cents a run | $6.121 cents a run | 2.3 times |
| A 40-turn agent task2,800,000 in, 40,000 out, 10 a day | $77.8826 cents a run | Too long for its window26 cents a run | |
| A support bot's reply4,000 in, 300 out, 2,000 a day | $84.600.14 cents a run | $37.800.063 cents a run | 2.2 times |
| Sort a message into a category250 in, 5 out, 50,000 a day | $1310.0087 cents a run | $60.750.004 cents a run | 2.2 times |
| Read an invoice into fields1,500 in, 250 out, 1,000 a day | $32.250.11 cents a run | $11.250.037 cents a run | 2.9 times |
| Review a pull request25,000 in, 4,500 out, 50 a day | $28.131.9 cents a run | $9.670.64 cents a run | 2.9 times |
Your own job on both
Start from a job, then set its size, how often it runs and whether the answers can wait. Both bills follow every change.
A short question and a few paragraphs back.
about 230 words
Instructions or documents the model has read before cost far less the second time.
about 380 words
A month of this job
- Gemini 2.5 Flash$4.02
0.13 cents a run
- GPT-4o mini$1.04
0.034 cents a run
GPT-4o mini saves $2.99 a month; Gemini 2.5 Flash costs 3.9 times as much.
This job on every modelWhy the price per token is only the start
Every maker prints 2 main prices: one for the tokens a model reads (input) and one for the tokens it writes (output). On most current models writing costs 3 to 5 times as much as reading, so which model is cheaper can depend on the job. A job that reads a long document and writes a line pays mostly the input price; a chat that writes paragraphs pays mostly the output price. That is why each comparison prices 8 jobs and not one figure.
The same text is not the same number of tokens on every model. Each maker cuts text its own way, and Anthropic says its models from Claude 4.7 on produce about 30 percent more tokens for the same text than earlier ones. A model with the lower price per token can still send the larger bill, so each comparison counts one of our lessons the way both makers count it.
Discounts change the order too. Work that can wait costs half on a batch at the makers that offer one, and text read again from a cache costs a quarter of the input price or less on every current model here. The price table on each comparison shows who offers what.
Thinking is billed as output, and models differ in how much they think and how long they answer. A price list cannot show that. Before you switch, run the same 10 tasks on both models and compare the bills.
Questions
- Which is cheaper, Gemini 2.5 Flash or GPT-4o mini?
- GPT-4o mini is cheaper: $0.15 per million tokens read and $0.60 per million written, against $0.30 and $2.50 on Gemini 2.5 Flash. On a mix of 3 tokens read for each 1 written, Gemini 2.5 Flash costs 3.2 times as much.
- Which is better, Gemini 2.5 Flash or GPT-4o mini?
- GPT-4o mini scores 127 on the Epoch Capabilities Index, an independent score from Epoch AI that combines over 50 benchmarks (GPT-5 is 150). Gemini 2.5 Flash has no independent score yet, so the only fair test is to run the same 10 tasks on both.
- What does a support bot cost a month on Gemini 2.5 Flash and GPT-4o mini?
- At 2,000 replies a day, each reading 4,000 tokens (50 percent of them from cache) and writing 300, it costs $84.60 a month on Gemini 2.5 Flash and $37.80 on GPT-4o mini: Gemini 2.5 Flash costs 2.2 times as much for this job.
- Which has the larger context window, Gemini 2.5 Flash or GPT-4o mini?
- Gemini 2.5 Flash, with 1.05M tokens against 128K on GPT-4o mini. The window holds your instructions, the files you attach, the conversation so far and the answer, all at once.
- Does the same text take the same number of tokens on Gemini 2.5 Flash and GPT-4o mini?
- No. Our lesson "How AI writes", 1,700 words long, is about 2,200 tokens on Gemini 2.5 Flash and about 2,100 on GPT-4o mini. Each maker cuts text its own way, and every extra token is paid for at the model's price.
- Can I pay less on Gemini 2.5 Flash and GPT-4o mini for work that can wait?
- On GPT-4o mini only: with a batch, where you collect the answers later, it costs $0.075 per million tokens read and $0.30 written. Google's price page lists no batch price for Gemini 2.5 Flash.
Sources